{"id":"W4409347493","doi":"10.1609/aaai.v39i16.33807","title":"OAC: Output-adaptive Calibration for Accurate Post-training Quantization","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Calibration; Quantization (signal processing); Training (meteorology); Computer science; Mathematics; Artificial intelligence; Algorithm; Statistics; Geography; Meteorology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002143506,0.001707826,0.001160134,0.0009697344,0.0006780063,0.001380695,0.002990832,0.001569607,0.007321118],"category_scores_gemma":[0.01305345,0.0006655872,0.0006503568,0.001092914,0.001202151,0.002977047,0.003038126,0.003085254,0.002893184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001044258,"about_ca_system_score_gemma":0.002351891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007736629,"about_ca_topic_score_gemma":0.01148438,"domain_scores_codex":[0.9983308,0.0003107734,0.0001212183,0.0003851946,0.0006965474,0.000155421],"domain_scores_gemma":[0.9966011,0.001062662,0.0002337883,0.0009376688,0.001071859,0.0000929083],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003925036,0.0001760186,0.001419575,0.0002332399,0.00009390719,0.0001459535,0.0002462153,0.1299796,0.02647693,0.01374099,0.01644416,0.8106509],"study_design_scores_gemma":[0.0000269672,0.0000574319,0.0003803288,0.00002428996,0.00001511118,0.00009371822,0.00003612015,0.9737091,0.01481135,0.00660844,0.004206914,0.00003019996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006318689,0.0004405152,0.9850358,0.0002063634,0.0001269617,0.0001049029,0.0001710688,0.006215876,0.001379824],"genre_scores_gemma":[0.2591631,0.0004800419,0.729311,0.0007629047,0.0001772823,0.0003920055,0.001313978,0.001583274,0.006816356],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007736629,"threshold_uncertainty_score":0.02449161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.159909562197313,"score_gpt":0.3845926615814959,"score_spread":0.2246830993841829,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}